Fast Human Detection via a Cascade of Neural Network Classifiers

摘要：

In this paper, we build a cascade of neural network classifiers for fast human detection. The human object is represented by a collection of blocks. For each block, the histogram of orientated gradients feature is extracted and a neural network classifier is built as weak hypothesis. Then these hypotheses are selected sequentially by Gentle Adaboost and the cascade structure is used to speedup the detector. Compared to global linear SVM classifiers, the new method gets better performance on the INRIA human detection database at a much faster speed.

关键词： component Human Detection Histogram of Oriented Gradients Gentle Adaboost Neural Network

作者: Yan Ren Bo Wang

作者单位: National Computer network Emergency Response technical Team/Coordination Center of China Beijing, China

会议类型: 国际会议

会议名称: 2010 The IET 3rd International Conference on Wireless,Mobile & Multimedia Networks(第三届IET无线移动及多媒体网络国际会议 ICWMMN 2010)

会议地点: 北京

会议语种:英文

页码: 323-326

在线出版日期: 2010-09-26（万方平台首次上网日期，不代表论文的发表时间）